Exploiting Independence in a Decentralised and Incremental Approach of Diagnosis

Marie-Odile Cordier, Alban Grastien

It is well-known that the size of the model is a bottleneck when using model-based approaches to diagnose complex systems. To answer this problem, decentralised/distributed approaches have been proposed. Another problem, which is far less considered, is the size of the diagnosis itself. However, it can be huge enough, especially in the case of on-line monitoring and when dealing with uncertain observations. We define two independence properties (state and transition-independence) and show their relevance to get a tractable representation of diagnosis in the context of both decentralised and incremental approaches. To illustrate the impact of these properties on the diagnosis size, experimental results on a toy example are given.

Subjects: 1.5 Diagnosis


Submitted: Oct 12, 2006

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.